A heterogeneous and fully parallel stereo matching algorithm for depth estimation, implementing a local adaptive support weight (ADSW) Guided Image Filter (GIF) cost aggregation stage. Developed in both C++ and OpenCL.

single and stereo calibration, disparity calculation.

Code for 'Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching'

Semi-Global Matching

Disparity maps using various algorithms

Code for "Unsupervised Adaptation for Deep Stereo" - ICCV17

C++ example codes for camera calibration, rectification and to build disparity maps

Implementation of simple block matching, block matching with dynamic programming and Stereo Matching using Belief Propagation algorithm for stereo disparity estimation

Compute disparity map from stereo image with semi global matching algorithm.

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator (RAL+ICRA'21)

C++ implementation of PatchMatch Stereo for images

Object tracking with OpenCV based on stereo camera images

Learning from scratch a confidence measure

Stereo matching algorithms implemented in MATLAB

ROS package for local obstacle avoidance using stereo RGB cameras on the Jackal

Pothole Detection Based on Disparity Transformation and Road Surface Modeling (T-IP)

[AI6121] Computer Vision is an elective course of MSAI, SCSE, NTU, Singapore. The repository corresponds to the AI6121 of Semester 1, AY2021-2022, starting from 08/2021. The instructor of this course is Prof. Lu Shijian.

2D Feature Detection and 3D point Clouds Generation, which can viewed in MeshLab or Blender

Stereo matching and sparse disparity map implementation using OpenCV (BRISK, ORB algorithms)